Table 3 Details of feature set data, including description, unit, mean, standard deviation and Pearson coefficient.

From: A method based on interpretable machine learning for recognizing the intensity of human engagement intention

Symbol

Description

Unit

Mean

Std

Pearson

Rg

Gaze intersection offset

mm

383.842

300.609

− 0.772

Rp

Offset of face towards intersection

mm

721.055

761.970

− 0.668

Tpz

Head translation variation z

mm

1043.253

302.724

− 0.628

Dist

Distance between the robot and the human

mm

1064.785

314.895

− 0.613

Exprs

Human facial expression

[1–3]

2.099

0.469

0.384

Vgry

Right eye sight direction vector y

0.185

0.162

0.366

Gpitch

Pitch angle of gaze

rad

0.186

0.169

0.335

Vgly

Left eye sight direction vector y

0.167

0.159

0.333

Vglx

Left eye sight direction vector x

0.054

0.243

0.214

Ppitch

Pitch angle of head pose

rad

0.136

0.155

0.208

Gyaw

Yaw angle of gaze

rad

− 0.031

0.255

0.191

Pyaw

Yaw angle of head pose

rad

0.068

0.311

− 0.168

Vgrx

Right eye sight direction vector x

− 0.113

0.237

0.159

Tpx

Head translation variation x

mm

23.490

155.871

− 0.154

Tpy

Head translation variation y

mm

− 58.452

173.342

− 0.139

Vgrz

Right eye sight direction vector z

− 0.931

0.058

− 0.108

Vglz

Left eye sight direction vector z

− 0.939

0.048

− 0.042

Proll

Roll angle of head pose

rad

− 0.112

0.145

− 0.021